Jev Decides, x402 Pays: The Decision-Only Model and Its Missing Payment Layer

TypeSafe AI, a two-year-old stealth startup founded by ex-OpenAI researcher Diogo Almeida and backed by a $40M DCVC-led seed round, launched Jev, a decision-only model that returns typed Choice, Score and Noul answers with calibrated confidence in a single forward pass at 70–500ms and $0.042 per million input tokens. The launch drew 140,000+ waitlist signups, 1,500+ Hacker News points and an llm-typesafe plugin from Simon Willison, who cautioned that a model returning only a floating-point number is "a regression even further towards black box machine learning." TypeSafe's own 20–200x faster and 40–400x cheaper figures are unvalidated, and the author notes that x402 micropayments on Base — with roughly 198.9M settlements worth ~$52.7M since May 2025 per TRM Labs, only 0.6–7.5% clearly agentic — are the natural billing layer for per-decision pricing.

Jev is a week old and already the most interesting model launch of September 2026. TypeSafe AI — founder Diogo Almeida ex-OpenAI, ChatGPT research , two years in stealth, $40M seed led by DCVC — shipped a model that refuses to generate text. You send it state text or JSON plus questions with predefined answers. It returns typed decisions: Choice one of up to 255 options , Score numeric rating , Noul yes/no with probability — each with calibrated confidence. All questions evaluate in one forward pass. 70–500ms. $0.042 per million input tokens, output free. Week-one traction is real: 140,000+ waitlist cleared in days, X trending, 12,759 tweets analyzed by OpenChamber, 1,500+ Hacker News points with 426 comments in a day, Vercel AI Gateway availability, and community builds jevchat, jev-2048, an open-weight "Kev" on Qwen . Simon Willison covered it and shipped an llm-typesafe plugin the next day. The "20–200x faster, 40–400x cheaper" figures are TypeSafe's own launch evaluations — not independently validated. Willison's critique is worth sitting with: a model that returns only a floating-point number is "a regression even further towards black box machine learning." Type safety constrains the form of the answer; decision quality still has to be measured separately. Jev is named for the Jevons-paradox insight: make a decision cheap enough and software makes far more of them. A 1,000-token decision costs about $0.000042 in model cost. That flips the business model. Every decision becomes a billable event, and subscriptions stop making sense at that unit size. The native billing is per-call micropayments: x402 — the server answers an unpaid request with a 402 Payment Required challenge price, asset, network, payTo , the buyer's wallet signs and retries, a facilitator settles on-chain. This isn't theoretical. ProBlocks runs a live x402 endpoint on Base at 0.001 USDC per call September 2026 . My own shop runs an x402 v2 payment contract live on Base — curl https://squeezeos-api.onrender.com/.well-known/x402 and you can inspect the manifest yourself payTo, facilitator, challenge headers . Honest context: TRM Labs Sept 9, 2026 counted ~198.9M x402 settlements worth ~$52.7M since May 2025, but only 0.6–7.5% of the value looks clearly agentic. The rail is proven; the agent economy on top is early. That's the opening. Every serious Jev integration converges on this it's in TypeSafe's launch materials : = 0.80 → auto-act no human in the loop 0.50–0.79 → advisory human sees decision + evidence < 0.50 → escalate human decides; log it — that's your tuning dataset python def route decision : c = decision.confidence if c = 0.80: return auto act decision if c = 0.50: return advisory decision log for review decision return escalate decision Production note: pin jev-1.13.0 , not the jev-latest alias — the alias moves when TypeSafe ships, and your tuned thresholds move with it. Disclosure: I run ScriptMasterLabs x402 payment rails on Base . The Jev facts above are third-party sourced with dates; the payments angle is where my shop lives.